© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28310
    Prev
    Next
    INDEX
    Explanations

    words related to assessment, judgment, or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Names or proper nouns containing specific phonetic patterns, primarily "is" followed by consonants like "s", "k", "l" or "e".

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugh
    -0.07
    _CID
    -0.06
    uty
    -0.06
    istrovstvÃŃ
    -0.06
    GPC
    -0.06
    ceptors
    -0.06
    наÑĢ
    -0.06
     surg
    -0.06
    aviors
    -0.06
     Rag
    -0.06
    POSITIVE LOGITS
    ellaneous
    0.10
    rael
    0.09
    patrick
    0.08
    abella
    0.08
    consin
    0.07
    antro
    0.07
    gerald
    0.07
    ahkan
    0.07
    elcome
    0.07
    sss
    0.07
    Activations Density 0.033%

    No Known Activations